Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 752 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.9546. Min Range: -4.9546

Max Act: 4.9546. Min Act: -0.1700

Data Index: 5403586 (Open Web Text)

Max Activating Token Index: 539

Text #1

Max Range: 4.9546. Min Range: -4.9546

Max Act: 4.6933. Min Act: -0.1700

Data Index: 6243193 (Open Web Text)

Max Activating Token Index: 884

Text #2

Max Range: 4.9546. Min Range: -4.9546

Max Act: 4.6986. Min Act: -0.1700

Data Index: 3844111 (Open Web Text)

Max Activating Token Index: 831

Text #3

Max Range: 4.9546. Min Range: -4.9546

Max Act: 4.7216. Min Act: -0.1700

Data Index: 6633927 (Open Web Text)

Max Activating Token Index: 387

Text #4

Max Range: 4.9546. Min Range: -4.9546

Max Act: 4.7508. Min Act: -0.1700

Data Index: 7572953 (Open Web Text)

Max Activating Token Index: 931

Text #5

Max Range: 4.9546. Min Range: -4.9546

Max Act: 4.7084. Min Act: -0.1700

Data Index: 623469 (Open Web Text)

Max Activating Token Index: 825

Text #6

Max Range: 4.9546. Min Range: -4.9546

Max Act: 4.6753. Min Act: -0.1700

Data Index: 3617510 (Open Web Text)

Max Activating Token Index: 684

Text #7

Max Range: 4.9546. Min Range: -4.9546

Max Act: 4.6409. Min Act: -0.1700

Data Index: 3283601 (Open Web Text)

Max Activating Token Index: 890

Text #8

Max Range: 4.9546. Min Range: -4.9546

Max Act: 4.5564. Min Act: -0.1700

Data Index: 2614816 (Open Web Text)

Max Activating Token Index: 301

Text #9

Max Range: 4.9546. Min Range: -4.9546

Max Act: 4.5754. Min Act: -0.1700

Data Index: 7945977 (Open Web Text)

Max Activating Token Index: 555

Text #10

Max Range: 4.9546. Min Range: -4.9546

Max Act: 4.6141. Min Act: -0.1700

Data Index: 6815379 (Open Web Text)

Max Activating Token Index: 314

Text #11

Max Range: 4.9546. Min Range: -4.9546

Max Act: 4.6099. Min Act: -0.1700

Data Index: 6332333 (Open Web Text)

Max Activating Token Index: 288

Text #12

Max Range: 4.9546. Min Range: -4.9546

Max Act: 4.6109. Min Act: -0.1700

Data Index: 4882446 (Open Web Text)

Max Activating Token Index: 1011

Text #13

Max Range: 4.9546. Min Range: -4.9546

Max Act: 4.5584. Min Act: -0.1700

Data Index: 7035891 (Open Web Text)

Max Activating Token Index: 144

Text #14

Max Range: 4.9546. Min Range: -4.9546

Max Act: 4.5639. Min Act: -0.1700

Data Index: 2276215 (Open Web Text)

Max Activating Token Index: 954

Text #15

Max Range: 4.9546. Min Range: -4.9546

Max Act: 4.5775. Min Act: -0.1700

Data Index: 3246371 (Open Web Text)

Max Activating Token Index: 733

Text #16

Max Range: 4.9546. Min Range: -4.9546

Max Act: 4.5488. Min Act: -0.1700

Data Index: 7401802 (Open Web Text)

Max Activating Token Index: 738

Text #17

Max Range: 4.9546. Min Range: -4.9546

Max Act: 4.4746. Min Act: -0.1700

Data Index: 6756665 (Open Web Text)

Max Activating Token Index: 635

Text #18

Max Range: 4.9546. Min Range: -4.9546

Max Act: 4.5643. Min Act: -0.1700

Data Index: 751829 (Open Web Text)

Max Activating Token Index: 501

Text #19

Max Range: 4.9546. Min Range: -4.9546

Max Act: 4.5677. Min Act: -0.1700

Data Index: 349046 (Open Web Text)

Max Activating Token Index: 854